Perceptron-based class verification

  • Authors:

  • Michael Gerber;Tobias Kaufmann;Beat Pfister

  • Affiliations:

  • Computer Engineering and Networks Laboratory, ETH Zurich, Switzerland;Computer Engineering and Networks Laboratory, ETH Zurich, Switzerland;Computer Engineering and Networks Laboratory, ETH Zurich, Switzerland

  • Venue:
  • NOLISP'07 Proceedings of the 2007 international conference on Advances in nonlinear speech processing
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a method to use multilayer perceptrons (MLPs) for a verification task, i.e. to verify whether two vectors are from the same class or not. In tests with synthetic data we could show that the verification MLPs are almost optimal from a Bayesian point of view. With speech data we have shown that verification MLPs generalize well such that they can be deployed as well for classes which were not seen during the training.